Optimización del clasificador “naive bayes” usando árbol de decisión C4.5
作者： Carlos Alarcón Jaimes
DOI:
关键词:
摘要: The Naive Bayes classifier is one of the most effective classification models, due to their simplicity, resistance noise, little processing time and high predictive power. assumes a strong assumption independence between predictor variables, which generally not met. Many studies seek improve power relaxing this independence, as selection subset variables that are independent or approximately independent. In paper, method seeks optimize using C4.5 decision tree presented. This selects in data set induced for go apply these selected variables. With previous use achieved removing redundant / irrelevant dataset choose those more informative tasks, thus classifier. illustrated three sets from UCI repository, Irvin Repository Machine Learning databases at University California National Household Survey Institute Statistics Informatics Peru, ENAHO INEI , implemented WEKA program.
unmsm.edu.pe参考文章(35)
Gregory M. Provan, Moninder Singh, Efficient learning of selective Bayesian network classifiers international conference on machine learning. pp. 453- 461 ,(1996)
Michael J. Pazzani, Eamonn J. Keogh, Learning augmented Bayesian classifiers: A comparison of distribution-based and classification-based approaches. international conference on artificial intelligence and statistics. ,(1999)
Hung-Ju Huang, Tzu-Tsung Wong, Why Discretization Works for Naive Bayesian Classifiers international conference on machine learning. pp. 399- 406 ,(2000)
Mehran Sahami, Learning limited dependence Bayesian classifiers knowledge discovery and data mining. pp. 335- 338 ,(1996)
I. Rish, An empirical study of the naive Bayes classifier ,(2001)
Michael J. Pazzani, An iterative improvement approach for the discretization of numeric attributes in Bayesian classifiers knowledge discovery and data mining. pp. 228- 233 ,(1995)
D Gunopulos, C Ratanamahatana, Selective Bayesian Classifier: Feature Selection For The Naive Bayesian Classifier Using Decision Trees WIT Transactions on Information and Communication Technologies. ,vol. 28, ,(2002) , 10.2495/DATA020591
Gregorio Perichinsky, Paola Verónica Britos, Arturo Carlos Servetto, Ramón García Martínez, J. Sicre, P. Felgaer, Optimización de redes bayesianas basado en técnicas de aprendizaje por inducción IX Congreso Argentino de Ciencias de la Computación. ,(2003)
Samuel D Pacheco Leal, Luis Gerardo Díaz Ortiz, Rodolfo García Flores, El clasificador Naive Bayes en la extracción de conocimiento de bases de datos Ingenierías (Nuevo León). ,vol. 8, pp. 24- 33 ,(2005)
Michael J. Pazzani, Pedro M. Domingos, Beyond Independence: Conditions for the Optimality of the Simple Bayesian Classifier. international conference on machine learning. pp. 105- 112 ,(1996)